© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 67022 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
67022

INDEX

Explanations

Warcraft

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fis

-0.06

accum

-0.06

Toolkit

-0.06

jections

-0.06

tp

-0.06

nr

-0.06

 perennial

-0.06

 retrie

-0.06

_rs

-0.06

th

-0.06

POSITIVE LOGITS

فور

0.07

 SOCIAL

0.07

陌

0.07

_THEME

0.07

셜

0.07

 Ambassador

0.07

沫

0.07

形势

0.07

ца

0.06

 Lenovo

0.06

Activations Density 0.004%

No Known Activations